spec+plan: consent-first, role-aware tutoring uplift (#8-#11)#12
Merged
Conversation
…gue /think + /spec-to-plan) Converged frame (27 claims, 17 honesty conditions) and 18-task/8-wave plan covering the four roadmap issues: #10 consent gate (both sign-in paths, no D1 write pre-consent), #11 versioned /learn-local Terms + Privacy, #8 roles + admin allow-list + approval-gated Bedrock-direct tutoring (Nova Pro via the OpenAI-compatible endpoint, Nova Sonic 2 via a serverless league-pattern voice bridge), #9 cloze contract kind + upstream content re-export. User decisions recorded in the frame: Bedrock-direct (no sibling model host), /learn-local policy docs, serverless-only plumbing (no EC2), consent+docs ship before any tutoring approval. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014QpvZY8K67Q9uGA6keFhTz
Contributor
Author
|
/agentic_review |
Code Review by QodoNew Review StartedThis review has been superseded by a new analysis |
PR Summary by QodoAdd consent-first, role-aware tutoring uplift spec + build plan (#8-#11)
AI Description
Diagram
High-Level Assessment
Files changed (8)
|
|
Code Review by Qodo
Context used✅ Tickets:
🎫 Learn: explicit user consent before saving learner data (consent gate + right to delete) 🎫 Learn content: strengthen curriculum upstream (french/spanish/culture-guide) + cloze exercises, then re-export 🎫 Learn: Terms of Use + Privacy Policy pages (versioned, linked from /learn, disclose Bedrock processing)✅ Compliance rules (platform):
9 rules 1. Doctor command inconsistent
|
![qodo-code-review[bot]](https://avatars.githubusercontent.com/in/484649?s=60&v=4){kind=small}
| - covers: c13, h5 | ||
| - acceptance: | ||
| - Signed-in non-approved POST /api/tutor gets 403 with ZERO outbound inference requests — extends the existing signed-out ordering test one level (h5) | ||
| - Approve/revoke is admin-only (allow-list enforced) and takes effect without re-login; learn admin verbs pass teken cli doctor --strict (explain catalog entries included) |
There was a problem hiding this comment.
1. Doctor command inconsistent 🐞 Bug ⚙ Maintainability
The new build plan documents teken cli doctor --strict, while other repo docs use `teken cli doctor . --strict`, creating inconsistent contributor guidance for running the rubric gate. This PR adds a new instance of the inconsistent form in both the human plan markdown and the exported devague plan JSON.
Agent Prompt
### Issue description
`docs/plans/2026-07-11-agentculture-org-learn-is-now-a-consent-first-role.md` (and the mirrored exported `.devague` plan JSON) uses `teken cli doctor --strict`, while other project docs (README/CLAUDE) commonly use `teken cli doctor . --strict`. This inconsistency makes it unclear what the canonical invocation is.
### Issue Context
The plan markdown and `.devague/plans/*.json` should be kept consistent with the repo’s established contributor instructions.
### Fix Focus Areas
- docs/plans/2026-07-11-agentculture-org-learn-is-now-a-consent-first-role.md[76-76]
- .devague/plans/agentculture-org-learn-is-now-a-consent-first-role.json[312-314]
### Suggested change
Update the plan text (and matching JSON) to use the same invocation as the Quickstart docs (e.g., `uv run teken cli doctor . --strict` or at least `teken cli doctor . --strict`), so all contributor instructions match.
ⓘ Copy this prompt and use it to remediate the issue with your preferred AI generation tools
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
The converged devague spec + 18-task build plan for the next /learn uplift, covering all four roadmap issues as one coherent phase: #8 (roles + approval-gated Bedrock tutoring), #9 (cloze contract kind + upstream content re-export), #10 (consent gate — the live gap), #11 (versioned Terms of Use + Privacy Policy).
docs/specs/2026-07-11-agentculture-org-learn-is-now-a-consent-first-role.md— the spec (27 claims, 17 confirmed honesty conditions, 3 nonblocking parked items)docs/plans/2026-07-11-agentculture-org-learn-is-now-a-consent-first-role.md— the plan (18 tasks, 8 dependency waves, 5 recorded risks).devague/frames/+.devague/plans/— the converged state (evidence trail for every confirmed claim)User decisions recorded in the frame
Key spec calls
handleCallbackAND device-flow poll both callupsertLearnertoday with no consent step)./api/tutoris 403 with zero outbound inference.Refs #8, #9, #10, #11. Spec/plan produced with /think + /spec-to-plan (devague 0.17.0); parked-vagueness resolutions hand-edited into the frame JSON per the known devague CLI gap.